Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for detecting vehicle maneuvers using a mobile phone residing in the vehicle, comprising: receiving, by a processor of the mobile phone, signals from two or more sensors residing in the mobile phone while the vehicle is moving, where the signals are indicative of vehicle movement and reported relative to a coordinate system associated with the mobile phone; converting, by the processor, the signals from the two or more sensors from the phone coordinate system to a geographic coordinate system; deriving, by the processor, a detection signal indicative of angular speed of the vehicle about a vertical axis of the geographic coordinate system, where the detection signal is derived from the converted signals; correlating, by the processor, the detection signal to one of a plurality of predefined signatures, where each signature represents a different maneuver made by a vehicle; determining, by the processor, a direction of travel for the vehicle; determining, by the processor, a horizontal displacement of the vehicle relative to the direction of travel; and identifying, by the processor, a maneuver made by the vehicle based on the correlation of the detected signal to one of the plurality of predefined signatures and magnitude of the horizontal displacement of the vehicle.
A method for detecting vehicle maneuvers using a mobile phone in the vehicle. The phone's processor receives signals from built-in sensors (like accelerometer, gyroscope) while the vehicle is moving. These signals, reported relative to the phone's coordinate system, indicate vehicle movement. The processor converts these signals to a geographic coordinate system, deriving a "detection signal" representing the vehicle's angular speed around a vertical axis. This signal is correlated to predefined maneuver signatures (lane change, turn, etc.). The system determines the vehicle's direction of travel and horizontal displacement, identifying the maneuver based on the signal correlation and displacement magnitude.
2. The method of claim 1 further comprises aligning the phone coordinate system with the geographic coordinate system prior to the step of receiving signals.
The vehicle maneuver detection method from the previous description first aligns the phone's coordinate system with the geographic coordinate system before receiving sensor signals. This alignment step improves the accuracy of the subsequent coordinate transformations and maneuver detection.
3. The method of claim 1 wherein the geographic coordinate system includes a vertical axis defined in relation to surface the vehicle is traversing upon and the vertical axis does not align with any of the axes that define the phone coordinate system.
In the vehicle maneuver detection method, the geographic coordinate system has a vertical axis that is defined relative to the road surface the vehicle is traveling on. Critically, this vertical axis is different and not aligned with any of the axes that define the mobile phone's internal coordinate system. This accounts for different phone orientations within the car.
4. The method of claim 1 wherein correlating the detection signal to one of a plurality of predefined signatures further comprises identifying one or two bumps in the detection signal, where one bump correlates to turn by the vehicle and two bumps correlates to a lane change by the vehicle.
In the vehicle maneuver detection method, correlating the detection signal to predefined signatures involves identifying "bumps" in the signal. One bump indicates a turn, while two bumps indicate a lane change. This bump-detection analysis of the angular speed signal allows for differentiating between different types of steering maneuvers.
5. The method of claim 1 wherein identifying a maneuver made by the vehicle further comprises classifying a vehicle maneuver into one of three classes selected from a group consisting of lane change, turn and curvy road.
In the vehicle maneuver detection method, identifying a maneuver means classifying it into one of three categories: lane change, turn, or driving on a curvy road. This categorization provides a high-level description of the vehicle's behavior.
6. The method of claim 1 wherein identifying a maneuver made by a vehicle further comprises comparing magnitude of the horizontal displacement to a threshold; and classifying the maneuver as a curvy road in response to a determination that the magnitude of the horizontal displacement exceeds the threshold.
In the vehicle maneuver detection method, identifying a maneuver includes comparing the horizontal displacement magnitude to a threshold. If the displacement exceeds the threshold, the maneuver is classified as driving on a curvy road. This helps distinguish between gradual curves and sharper turns or lane changes.
7. The method of claim 6 wherein the velocity of the vehicle is determined from readings of a global positioning system (GPS) residing in the mobile phone.
In the curvy road detection method from the previous description, the vehicle's velocity is determined using GPS readings from the mobile phone. This velocity information is used in conjunction with the angular speed to accurately determine horizontal displacement and classify maneuvers.
8. The method of claim 1 wherein determining horizontal displacement further comprises determining velocity of the vehicle along the direction of travel; determining angular speed of the vehicle about a vertical axis of the geographic coordinate system; and determining horizontal displacement as a function of velocity and angular speed of the vehicle.
In the vehicle maneuver detection method, determining horizontal displacement involves: finding the vehicle's velocity along its direction of travel, determining the vehicle's angular speed about a vertical axis, and calculating horizontal displacement as a function of both velocity and angular speed.
9. The method of claim 1 further comprises determining a difference in vehicle heading angle between start and end of vehicle maneuver; and further classifying a turn as either a right turn, a left turn or a U-turn in accordance with the difference in vehicle heading angle.
The vehicle maneuver detection method further involves determining the difference in vehicle heading angle between the start and end of a maneuver. Based on this heading angle difference, a turn is further classified as either a right turn, a left turn, or a U-turn, providing a more detailed maneuver description.
10. The method of claim 1 further comprises measuring motion of the vehicle using a motion sensor residing in the mobile phone.
The vehicle maneuver detection method also involves measuring the vehicle's motion using a motion sensor in the mobile phone. This sensor data provides additional information for maneuver detection and classification.
11. The method of claim 10 wherein the motion sensor is further defined as at least one of a gyroscope or an accelerometer.
In the vehicle maneuver detection method, the motion sensor is either a gyroscope, an accelerometer, or both. These sensors provide complementary data about the vehicle's movement.
12. A method for detecting vehicle maneuvers using a computing device in a vehicle, comprising: receiving, by a processor of the computing device, a signal from an inertial sensor of the computing device while the vehicle is moving, where the signal is indicative of angular speed of the vehicle about a vertical axis; detecting, by the processor, one or more pulses in the signal within a fixed time period, where one pulse with the fixed time period correlates to a possible turn by the vehicle and two pulses within the fixed time period correlates to a possible lane change by the vehicle; determining, by the processor, a direction of travel for the vehicle; determining, by the processor, a horizontal displacement of the vehicle relative to the direction of travel; comparing, by the processor, magnitude of the horizontal displacement to a first threshold, where the comparison is performed in response to detecting two pulses in the signal; classifying vehicle maneuver as a curvy road in response to a determination that the magnitude of the horizontal displacement exceeds the first threshold; and classifying vehicle maneuver as a lane change in response to a determination that the magnitude of the horizontal displacement is less than the first threshold.
A method detects vehicle maneuvers using a computing device's (e.g. phone, car console) inertial sensor. The sensor reports the vehicle's angular speed about a vertical axis. The processor detects pulses in the signal within a fixed time. One pulse suggests a turn, two pulses a lane change. The system determines the vehicle's travel direction and horizontal displacement, then compares the displacement to a threshold. If two pulses are detected and displacement exceeds the threshold, it is classified as a curvy road; otherwise, a lane change.
13. The method of claim 12 further comprises detecting two pulses in the signal within the fixed time period; determining, by the processor, whether amplitude of first pulse of the two detected pulses is higher or lower than a baseline value; classifying the vehicle maneuver as a possible change to left lane in response to determining that the amplitude of the first pulse is higher than a baseline value; and classifying the vehicle maneuver as a possible change to right lane in response to determining that the amplitude of the first pulse is lower than a baseline value.
The lane change detection method builds upon the previous description by determining whether the amplitude of the first pulse in the detected two-pulse signal is higher or lower than a baseline value. If higher, it suggests a left lane change; if lower, a right lane change. This allows distinguishing between left and right lane changes.
14. The method of claim 12 further comprises determining, by the processor, whether amplitude of the one detected pulse is higher or lower than a baseline value; classifying the vehicle maneuver as a possible left turn in response to determining that the amplitude of the one detected pulse is higher than a baseline value; and classifying the vehicle maneuver as a possible right turn in response to determining that the amplitude of the one detected pulse is lower than a baseline value.
The turn detection method expands upon the core method. The system determines whether the amplitude of a single detected pulse is higher or lower than a baseline value. A higher amplitude suggests a possible left turn, while a lower amplitude suggests a possible right turn.
15. The method of claim 14 further comprises comparing, by the processor, magnitude of the horizontal displacement to a right turn threshold, where the comparison is performed in response to classifying the vehicle maneuver as a possible right turn; classifying vehicle maneuver as a curvy road in response to a determination that the magnitude of the horizontal displacement exceeds the right turn threshold; and classifying vehicle maneuver as a right turn in response to a determination that the magnitude of the horizontal displacement is less than the right turn threshold.
The right turn detection method refines the turn detection. It compares the horizontal displacement magnitude to a "right turn threshold" after a possible right turn is classified. If the displacement exceeds the threshold, it's classified as a curvy road; otherwise, it's classified as a right turn.
16. The method of claim 15 further comprises comparing, by the processor, magnitude of the horizontal displacement to a left turn threshold, where the comparison is performed in response to classifying the vehicle maneuver as a possible left turn; classifying vehicle maneuver as a curvy road in response to a determination that the magnitude of the horizontal displacement exceeds the left turn threshold; and classifying vehicle maneuver as a right turn in response to a determination that the magnitude of the horizontal displacement is less than the left turn threshold, where the value of the left turn threshold differs from value of the right turn threshold.
The left turn detection method builds upon the right turn detection. After classifying a possible left turn, it compares the horizontal displacement magnitude to a "left turn threshold". Displacement exceeding the threshold results in curvy road classification; otherwise, a left turn. The left turn threshold's value differs from the right turn threshold.
17. The method of claim 12 further comprises converting, by the processor, the signal a device coordinate system to a geographic coordinate system, where wherein the signal is reported in the device coordinate system and the geographic coordinate system includes a vertical axis defined in relation to surface the vehicle is traversing upon and the vertical axis does not align with any of the axes that define the phone coordinate system.
In the vehicle maneuver detection method, the inertial sensor signal, reported in the device's coordinate system, is converted to a geographic coordinate system. The geographic system uses a vertical axis related to the road surface, distinct from the device's coordinate axes.
18. The method of claim 12 wherein determining horizontal displacement further comprises determining velocity of the vehicle along the direction of travel; determining angular speed of the vehicle about a vertical axis of the geographic coordinate system; and determining horizontal displacement as a function of velocity and angular speed of the vehicle.
In the vehicle maneuver detection method, horizontal displacement determination involves calculating the vehicle's velocity along its travel direction, determining the angular speed around a vertical axis, and computing the horizontal displacement based on velocity and angular speed.
19. The method of claim 18 wherein the velocity of the vehicle is determined from readings of a global positioning system (GPS) residing in the mobile phone.
In the vehicle maneuver detection method from the previous description, the vehicle's velocity is determined using GPS readings from the mobile phone. This provides a location-based measure of speed.
20. The method of claim 12 further comprises measuring the angular speed of the vehicle about a vertical axis using the inertial sensor in the computing device.
In the vehicle maneuver detection method, the angular speed of the vehicle about the vertical axis is measured using the inertial sensor in the computing device. This sensor directly provides the angular speed data needed for analysis.
Unknown
December 5, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.